Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases involving mathematical or formal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.97
    。
    -0.72
    ↵
    -0.63
    ].
    -0.58
    ).
    -0.57
    ".
    -0.57
    ..
    -0.56
     .
    -0.53
    2
    -0.51
    ”.
    -0.51
    POSITIVE LOGITS
     propOrder
    1.03
    ',
    0.99
    $")
    0.97
    httphttps
    0.95
    ?')
    0.95
    "},
    0.94
    '},
    0.92
    0.92
    AccessorTable
    0.91
    '),
    0.90
    Act Density 0.476%

    No Known Activations